Products · Asustor · NAS
Asustor Flashstor 12 Pro Gen3 (FS812X1)
- Processor
- AMD Ryzen 5 PRO 8640U
- Memory (RAM)
- 16 or 96 GB
- Released
- 2026
Configurations
Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.
| Configuration | Memory | Usable for AI | Bandwidth | LLMs that run well | Launch price |
|---|---|---|---|---|---|
| AMD Ryzen 5 PRO 8640U | 16.0 GB | 12.0 GB | 77 GB/s | 311 of 622 | — |
| AMD Ryzen 5 PRO 8640U · upgraded to the maker's maximum | 96.0 GB | 83.5 GB | 77 GB/s | 363 of 622 | — |
Specifications 96.0 GB configuration
| Maker | Asustor |
|---|---|
| Type | NAS |
| Processor | AMD Ryzen 5 PRO 8640U NAS (96 GB) · upgraded to the maker's maximum |
| Memory (RAM) | 96.0 GB |
| Usable for AI models | 83.5 GB |
| Memory bandwidth | 77 GB/s |
| FP16 compute | 0.5 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 12x M.2 NVMe (PCIe 4.0: 1x x4, 4x x2, 2x x1; PCIe 3.0: 3x x2, 2x x1) |
| NAS system | ADM |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR5-5600 SO-DIMM (ECC shipped) · 2 slots · up to 96.0 GB per the maker · ECC |
| Availability | Announced, not on general sale when checked |
| Notes | AMD Ryzen 5 PRO 8640U (3.5-4.9 GHz). Ryzen 5 PRO 8640U (6C/12T Zen 4) with Radeon 760M graphics, a Ryzen AI NPU and up to 96 GB DDR5 is the strongest AI hardware Asustor has shown. Announced or in crowdfunding; not on general sale when checked (November 2026). |
| Product page | www.asustor.com (opens in a new tab) |
Running AI on the Asustor Flashstor 12 Pro Gen3 (FS812X1)
Yes, it runs AI models on the NAS itself. Models run on its CPU cores, and this configuration leaves about 83.5 GB for them after the NAS system and its storage services. The grades below assume the NAS isn’t busy with backups or media work at the same time. More memory is the upgrade that matters most: see the configurations.
Apps you can install to run models
| App | How it installs |
|---|---|
| Ollama / Open WebUI / other containers via Docker Engine + Portainer CE | In a container (Docker) |
AI features from Asustor
| Feature | What it does | Where the AI runs |
|---|---|---|
| Photo Gallery AI Search / Category Albums (beta, Photo Gallery 4.1) | Natural-language photo search and automatic category albums in Asustor's Photo Gallery app (beta since Photo Gallery 4.1.0). Asustor's Computex 2026 release says its AI features are optional and 'completely local'. | On the NAS |
Best LLMs for the Asustor Flashstor 12 Pro Gen3 (FS812X1) 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 55.1 GB | 17.8 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder Next (80B-A3B) | Q4_K_M | 56.1 GB | 20.3 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q4_K_M | 57.1 GB | 20.3 tok/s | Runs well |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Next 80B-A3B Instruct | Q4_K_M | 57.1 GB | 20.3 tok/s | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 74.2 GB | 13.1 tok/s | Runs welltight fit |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Super VL 120B-A12B | Q4_K_M | 83.3 GB | 5.4 tok/s | Slowtight fit |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q4_K_M | 31.8 GB | 24.1 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q4_K_M | 29.4 GB | 20.3 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 28.9 GB | 20.3 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q4_K_M | 29.4 GB | 20.3 tok/s | Runs well |
Best Image models for the Asustor Flashstor 12 Pro Gen3 (FS812X1) 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | FP16 | 57.0 GB | 74.8 min | Very slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | FP16 | 57.3 GB | 31.2 min | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | Q8 GGUF | 61.9 GB | 51.6 min | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Text2Image (64B) | FP8 | 69.1 GB | 44.9 min | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2512 | FP16 | 63.8 GB | 1.9 h | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 72.0 GB | 11.2 min | Very slowtight fit |
Best Video models for the Asustor Flashstor 12 Pro Gen3 (FS812X1) 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | Q8 GGUF | 68.2 GB | 24.9 h | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q8 GGUF | 49.8 GB | 2.2 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | FP16 | 58.0 GB | 33.2 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | FP16 | 58.0 GB | 33.2 h | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 1.5 (8.3B) | FP16 | 55.2 GB | 37.4 h | Very slow |
Best Decision models for the Asustor Flashstor 12 Pro Gen3 (FS812X1) 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | F16 | 3.8 GB | 75 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 8.2 GB | 1.4 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 610 ms | Slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 11.8 GB | 9.3 s | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 8.2 GB | 1.4 s | Very slow |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 180 ms | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q8_0 | 16.3 GB | 18.9 s | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 37.1 s | Very slow |
Other products with the AMD Ryzen 5 PRO 8640U NAS (96 GB)
Spec sources
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.